© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8055
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     choice
    -0.27
    лÑĮн
    -0.27
    æĪij们è¦ģ
    -0.27
     bumper
    -0.25
    uggy
    -0.25
    ä¼ļè§ģ
    -0.24
    zik
    -0.24
     Trust
    -0.23
     Lad
    -0.23
    advertisement
    -0.23
    POSITIVE LOGITS
    precation
    0.27
    GA
    0.27
    onacci
    0.26
     perfection
    0.26
     remind
    0.25
    å°ijè§ģ
    0.25
    ç¥ŀéĢļ
    0.25
    FR
    0.25
     perfect
    0.25
    è§ĨåIJ¬
    0.25
    Activations Density 0.011%

    No Known Activations